Learning view invariant gait features with Two-Stream GAN | |
Wang, Yanyun1,2; Song, Chunfeng2,3; Huang, Yan2,3,4; Wang, Zhenyu1; Wang, Liang2,3,4 | |
发表期刊 | NEUROCOMPUTING |
ISSN | 0925-2312 |
2019-04-28 | |
卷号 | 339期号:2019页码:245-254 |
摘要 | Gait recognition is an important yet challenging problem in computer vision. The changing view of gait is one of the most challenging factors, which could greatly affect the accuracy of cross-view gait recognition. In this paper, we propose a Two-Stream Generative Adversarial Network (TS-GAN) for cross-view gait recognition. For any view of gait representations, GAN can restore it to the corresponding standard view, to learn view invariant gait features. To achieve this goal, TS-GAN has two streams : (1) the global-stream can learn global contexts, and (2) the part-stream can learn local details. We combine the two streams to learn final identities. Moreover, we add a pixel-wise loss along with the generators of GAN to restore the gait details in pixel-level. We evaluate the proposed method on two widely used gait databases: CASIA-B and OU-ISIR. Experiment results show that our approach outperforms the compared state-of-the-art approaches. (C) 2019 Elsevier B.V. All rights reserved. |
关键词 | Gait recognition Cross-veiw Two-Stream GAN |
DOI | 10.1016/j.neucom.2019.02.025 |
关键词[WOS] | RECOGNITION ; REPRESENTATION ; IMAGE |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Fundamental Research Funds for the Central Universities[2018ZD05] ; National National Science Foundation of China[61420106015] ; National National Science Foundation of China[61721004] ; National National Science Foundation of China[61633021] ; National National Science Foundation of China[61525306] ; National National Science Foundation of China[61573139] ; National Key Research and Development Program of China[2016YFB10010 0 0] ; Beijing Science and Technology Project[Z181100008918010] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; Beijing Science and Technology Project[Z181100008918010] ; National Key Research and Development Program of China[2016YFB10010 0 0] ; National National Science Foundation of China[61573139] ; National National Science Foundation of China[61525306] ; National National Science Foundation of China[61633021] ; National National Science Foundation of China[61721004] ; National National Science Foundation of China[61420106015] ; Fundamental Research Funds for the Central Universities[2018ZD05] |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000461166500024 |
出版者 | ELSEVIER SCIENCE BV |
七大方向——子方向分类 | 生物特征识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/25005 |
专题 | 智能感知与计算 |
通讯作者 | Wang, Zhenyu |
作者单位 | 1.North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China 2.Chinese Acad Sci CASIA, CRIPAC, NLPR, Beijing 100190, Peoples R China 3.UCAS, Beijing 100190, Peoples R China 4.CEBSIT, Beijing 100190, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Wang, Yanyun,Song, Chunfeng,Huang, Yan,et al. Learning view invariant gait features with Two-Stream GAN[J]. NEUROCOMPUTING,2019,339(2019):245-254. |
APA | Wang, Yanyun,Song, Chunfeng,Huang, Yan,Wang, Zhenyu,&Wang, Liang.(2019).Learning view invariant gait features with Two-Stream GAN.NEUROCOMPUTING,339(2019),245-254. |
MLA | Wang, Yanyun,et al."Learning view invariant gait features with Two-Stream GAN".NEUROCOMPUTING 339.2019(2019):245-254. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Two-stream gan for g(2222KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论